What Gets Cited: Competitive GEO in AI Answer Engines
The paper titled 'What Gets Cited: Competitive GEO in AI Answer Engines' explores how AI answer engines cite sources. It identifies key factors influencing citation, such as topical relevance and list position. The authors provide a reproducible evaluation protocol and a GEO checklist for practitioners based on their findings.
- ▪AI answer engines generate answers from retrieved pages but cite only a few sources.
- ▪The study executed 252,000 trials across six LLMs to determine citation influences.
- ▪Topical relevance and list position were found to be the biggest drivers of being cited first.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.25517 (cs) [Submitted on 25 May 2026] Title:What Gets Cited: Competitive GEO in AI Answer Engines Authors:Rahul Vishwakarma, Shushant Kumar, Ratnesh Jamidar View a PDF of the paper titled What Gets Cited: Competitive GEO in AI Answer Engines, by Rahul Vishwakarma and 2 other authors View PDF HTML (experimental) Abstract:AI answer engines generate answers from retrieved pages but cite only a few sources. This makes visibility depend not just on ranking, but on being cited.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
